Computer supported environment for automatically prioritizing electronic messages based on importance to the sender

Abstract

A method includes analyzing a content of an electronic message associated with a sender. A score associated with the electronic message is generated. The score is indicative of an importance of the electronic message to the sender. The electronic message is automatically flagging based on the score. The flagged electronic message is transmitted to a recipient

1 . A method, comprising:
 analyzing a content of an electronic message associated with a sender prior to transmission of the electronic message to a recipient of the electronic message;   generating a score associated with the electronic message prior to the transmission of the electronic message to the recipient of the electronic message, wherein the score is indicative of an importance of the electronic message to the sender and wherein the score is generated based on the analyzing the content;   automatically flagging the electronic message based on the score prior to the transmission of the electronic message to the recipient of the electronic message; and   transmitting the flagged electronic message to a recipient.   
     
     
         2 . The method as described in  claim 1  further comprising tracking whether the electronic message is read by the recipient after transmission of the flagged electronic message. 
     
     
         3 . The method as described in  claim 2  further comprising automatically sending a follow up electronic message responsive to determining that the electronic message is unread by the recipient and after a predetermined amount of time has expired. 
     
     
         4 . The method as described in  claim 2 , wherein the tracking occurs responsive to the score exceeding a predetermined threshold. 
     
     
         5 . The method as described in  claim 1  further comprising:
 determining a relationship between the sender and the recipient of the electronic message; and 
 determining importance of the relationship between the sender and the recipient via applying one of a machine learning supervised algorithm, a machine learning unsupervised algorithm, a machine learning semi-supervised algorithm, or a machine learning association rules to the determined relationship, and wherein the generating the score is further based on the determined importance of the relationship between the sender and the recipient. 
 
     
     
         6 . The method as described in  claim 5 , wherein the machine learning supervised algorithm is one of a classification, a regression, or a similarity learning algorithm. 
     
     
         7 . The method as described in  claim 5 , wherein the machine learning association rules is one of a learning classifier systems, or an inductive logic programming. 
     
     
         8 . The method as described in  claim 1 , wherein the analyzing identifies urgent terms within the electronic message, and wherein the method further comprises applying a decision tree machine learning model, a regression analysis machine learning model, or a Baysian network machine learning model to the identified urgent terms to determine a relationship between the electronic message and a priority of the electronic message to the sender, and wherein the generating the score is further based on the relationship between the electronic message and the priority of the electronic message to the sender. 
     
     
         9 . The method as described in  claim 1  further comprising determining a strength of a relationship between the sender and the recipient, wherein the determining the strength is based on at least one of a frequency of face-to-face interaction between the sender and the recipient, a frequency of electronic communication between the sender and the recipient, a quantity of electronic communication between the sender and the recipient, types of electronic communication between the sender and the recipient, duration of face-to-face interaction between the sender and the recipient, duration of electronic communication between the sender and the recipient, or presence or absence of other participants, and wherein the generating the score is further based on the strength of the relationship between the sender and the recipient. 
     
     
         10 . A system for determining importance of an electronic message to a sender, the system comprising:
 a processor;   a memory operatively connected to the processor and storing instruction that, when executed by the processor, cause:
 analyzing a content of an electronic message associated with a sender prior to transmission of the electronic message to a recipient of the electronic message; 
 generating a score associated with the electronic message prior to the transmission of the electronic message to the recipient of the electronic message, wherein the score is indicative of an importance of the electronic message to the sender and wherein the score is generated based on the analyzing the content; 
 automatically flagging the electronic message based on the score prior to the transmission of the electronic message to the recipient of the electronic message; and 
 transmitting the flagged electronic message to a recipient. 
   
     
     
         11 . The system as described in  claim 10 , wherein instructions executed by the processor further cause:
 tracking whether the electronic message is read by the recipient after transmission of the flagged electronic message; and   automatically sending a follow up electronic message responsive to determining that the electronic message is unread by the recipient and after a predetermined amount of time has expired.   
     
     
         12 . The system as described in  claim 10 , wherein instructions when executed by the processor further cause:
 determining a relationship between the sender and the recipient of the electronic message; and   determining importance of the relationship between the sender and the recipient via applying one of a machine learning supervised algorithm, a machine learning unsupervised algorithm, a machine learning semi-supervised algorithm, or a machine learning association rules to the determined relationship, and wherein the generating the score is further based on the determined importance of the relationship between the sender and the recipient.   
     
     
         13 . The system as described in  claim 12 , wherein the machine learning supervised algorithm is one of a classification, a regression, or a similarity learning algorithm. 
     
     
         14 . The system as described in  claim 10 , wherein the analyzing identifies urgent terms within the electronic message, and wherein the instructions when executed by the processor further cause applying a decision tree machine learning model, a regression analysis machine learning model, or a Baysian network machine learning model to the identified urgent terms to determine a relationship between the electronic message and a priority of the electronic message to the sender, and wherein the generating the score is further based on the relationship between the electronic message and the priority of the electronic message to the sender. 
     
     
         15 . The system as described in  claim 10 , wherein the instructions when executed by the processor further cause determining a strength of a relationship between the sender and the recipient based on at least one of a frequency of face-to-face interaction between the sender and the recipient, a frequency of electronic communication between the sender and the recipient, a quantity of electronic communication between the sender and the recipient, types of electronic communication between the sender and the recipient, duration of face-to-face interaction between the sender and the recipient, duration of electronic communication between the sender and the recipient, or presence or absence of other participants, and wherein the generating the score is further based on the strength of the relationship between the sender and the recipient. 
     
     
         16 . A non-transitory, computer-readable medium storing a set of instructions that, when executed by a processor, cause:
 analyzing a content of an electronic message associated with a sender prior to transmission of the electronic message to a recipient of the electronic message;   generating a score associated with the electronic message prior to the transmission of the electronic message to the recipient of the electronic message, wherein the score is indicative of an importance of the electronic message to the sender and wherein the score is generated based on the analyzing the content;   automatically flagging the electronic message based on the score prior to the transmission of the electronic message to the recipient of the electronic message; and   transmitting the flagged electronic message to a recipient.   
     
     
         17 . The non-transitory as described in  claim 16  further comprising:
 tracking whether the electronic message is read by the recipient after transmission of the flagged electronic message; and 
 automatically sending a follow up electronic message responsive to determining that the electronic message is unread by the recipient and after a predetermined amount of time has expired. 
 
     
     
         18 . The non-transitory as described in  claim 16  further comprising:
 determining a relationship between the sender and the recipient of the electronic message; and 
 determining importance of the relationship between the sender and the recipient via applying one of a machine learning supervised algorithm, a machine learning unsupervised algorithm, a machine learning semi-supervised algorithm, or a machine learning association rules to the determined relationship, and wherein the generating the score is further based on the determined importance of the relationship between the sender and the recipient. 
 
     
     
         19 . The non-transitory as described in  claim 16 , wherein the analyzing identifies urgent terms within the electronic message, and wherein the instructions when executed by the processor further cause applying a decision tree machine learning model, a regression analysis machine learning model, or a Baysian network machine learning model to the identified urgent terms to determine a relationship between the electronic message and a priority of the electronic message to the sender, and wherein the generating the score is further based on the relationship between the electronic message and the priority of the electronic message to the sender. 
     
     
         20 . The non-transitory as described in  claim 20 , wherein the instructions when executed by the processor further cause determining a strength of a relationship between the sender and the recipient based on at least one of a frequency of face-to-face interaction between the sender and the recipient, a frequency of electronic communication between the sender and the recipient, a quantity of electronic communication between the sender and the recipient, types of electronic communication between the sender and the recipient, duration of face-to-face interaction between the sender and the recipient, duration of electronic communication between the sender and the recipient, or presence or absence of other participants, and wherein the generating the score is further based on the strength of the relationship between the sender and the recipient.